Context-aware user preferences prediction on location-based social networks

Recently, the increasing number of mobile users in location-based social networks (LBSNs) has generated large amounts of data, which provides unprecedented opportunities to study mobile user preferences for location recommendation. However, the huge amount of LBSNs data and sparsity problem limited improvements of efficiency and accuracy on mobile user preferences for location recommendation. This paper proposes a context-aware user preferences prediction algorithm for location recommendation on LBSNs. It introduces cloud model and category information into estimating the similarity of users and locations. Furthermore, it predicts user preferences of new locations according to the categories of new locations and user visited. In particular, the algorithm is parallelized with MapReduce framework for significant improvement in efficiency. Experimental results on Foursquare dataset demonstrate the performance gains of the algorithm.